Feb 8, 2022 · A method that captures resolution-free object contours as complex periodic functions. The method offers a good compromise between accuracy and compactness.
scholar.google.com › citations
While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative represen- tations such as polygons or active ...
The method offers a good compromise between accuracy and compactness thanks to the design of efficient geometric shape priors. We benchmark SCR on the popular ...
SCR: Smooth Contour Regression with Geometric Priors ... While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative ...
SCR: Smooth Contour Regression with Geometric Priors · no code implementations • 8 Feb 2022 • Gaetan Bahl, Lionel Daniel, Florent Lafarge. While object ...
I am a researcher at Inria in the Titane research group. I do research in Computer Vision, Geometry Processing and Remote Sensing.
SCR: Smooth Contour Regression with Geometric Priors. G Bahl, L Daniel, F Lafarge. arXiv preprint arXiv:2202.03784, 2022. 1, 2022. Scanner Neural Network for On ...
Share SCR: Smooth Contour Regression with Geometric Priors - IRT Saint Exupéry - Institut de Recherche Technologique.
from publication: SCR: Smooth Contour Regression with Geometric Priors | While object detection methods traditionally make use of pixel-level masks or ...
SCR: Smooth Contour Regression with Geometric Priors · Gaétan Bahl, Lionel Daniel, Florent Lafarge. 2022 (modified: 03 Nov 2022); CoRR 2022; Readers: Everyone ...